Training in progress, epoch 6, checkpoint
Browse files- .gitattributes +1 -0
- checkpoint-93522/README.md +202 -0
- checkpoint-93522/adapter_config.json +34 -0
- checkpoint-93522/adapter_model.safetensors +3 -0
- checkpoint-93522/optimizer.pt +3 -0
- checkpoint-93522/rng_state_0.pth +3 -0
- checkpoint-93522/rng_state_1.pth +3 -0
- checkpoint-93522/rng_state_2.pth +3 -0
- checkpoint-93522/rng_state_3.pth +3 -0
- checkpoint-93522/rng_state_4.pth +3 -0
- checkpoint-93522/rng_state_5.pth +3 -0
- checkpoint-93522/rng_state_6.pth +3 -0
- checkpoint-93522/rng_state_7.pth +3 -0
- checkpoint-93522/scaler.pt +3 -0
- checkpoint-93522/scheduler.pt +3 -0
- checkpoint-93522/special_tokens_map.json +17 -0
- checkpoint-93522/tokenizer.json +3 -0
- checkpoint-93522/tokenizer_config.json +2063 -0
- checkpoint-93522/trainer_state.json +1575 -0
- checkpoint-93522/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -38,3 +38,4 @@ checkpoint-31174/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 38 |
checkpoint-46761/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
checkpoint-62348/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
checkpoint-77935/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 38 |
checkpoint-46761/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
checkpoint-62348/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
checkpoint-77935/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
checkpoint-93522/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-93522/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-3.2-1B
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.15.2
|
checkpoint-93522/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-3.2-1B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 8,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"q_proj",
|
| 28 |
+
"v_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"trainable_token_indices": null,
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-93522/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0d0259157a77513d9ac320694d9f347a845c305305c99e8c1c08e80a07282d4
|
| 3 |
+
size 3416264
|
checkpoint-93522/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4c0de869bdd2bba639d0f66fcaa0dc8789defc61f0789a6d6b75376da702b07
|
| 3 |
+
size 6870283
|
checkpoint-93522/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f482fbf563aa55156e02ea829bbaee02e7782263637ef2f9edd93bbc394a5a64
|
| 3 |
+
size 16389
|
checkpoint-93522/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:703ee74e71bea7271296b9a28d200c5f7b640ee1dca4dce2b4946ce4db48f685
|
| 3 |
+
size 16389
|
checkpoint-93522/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7d3c9e3db1b5be998f66d2ab909ca1891cbfead5e2ccfd820524229fdd099bb
|
| 3 |
+
size 16389
|
checkpoint-93522/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0ab3ce70be83d80de8ec0ae1bf5c1fc8e2d6a75d904aa781e2b4a4ac2dba1c9
|
| 3 |
+
size 16389
|
checkpoint-93522/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fac85003d2c922bd92fb083dddf14f62d692e44f6920b5e3d374f5d09a9e97f
|
| 3 |
+
size 16389
|
checkpoint-93522/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa87f8e80256d1d07366e1393716b359fed6de76ea46e5fa2373fc4ac1a62710
|
| 3 |
+
size 16389
|
checkpoint-93522/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:096b833f6d0d40db17080e881c8aaa0e525e305185aac486d52f099b2d9d8f03
|
| 3 |
+
size 16389
|
checkpoint-93522/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2e7a225e4814d63f5e24a1376f08e7365bd53ecb4e4de8f5d2c833365c2709b
|
| 3 |
+
size 16389
|
checkpoint-93522/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3082961a11b16cea90a0bb3569106f2ef22d825eade3f40c3d7546a278b7f4c
|
| 3 |
+
size 1383
|
checkpoint-93522/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34a88a4192a912d163a59224a4a8e7e6d5c6ca46e200a51a81875309a814d48f
|
| 3 |
+
size 1465
|
checkpoint-93522/special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|end_of_text|>"
|
| 17 |
+
}
|
checkpoint-93522/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
checkpoint-93522/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"clean_up_tokenization_spaces": true,
|
| 2054 |
+
"eos_token": "<|end_of_text|>",
|
| 2055 |
+
"extra_special_tokens": {},
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|end_of_text|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
+
}
|
checkpoint-93522/trainer_state.json
ADDED
|
@@ -0,0 +1,1575 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.0,
|
| 6 |
+
"eval_steps": 3118,
|
| 7 |
+
"global_step": 93522,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.032079042761364,
|
| 14 |
+
"grad_norm": 1.7145991325378418,
|
| 15 |
+
"learning_rate": 0.0007978742969568658,
|
| 16 |
+
"loss": 0.4787,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.064158085522728,
|
| 21 |
+
"grad_norm": 1.2714065313339233,
|
| 22 |
+
"learning_rate": 0.0007957357627082398,
|
| 23 |
+
"loss": 0.3972,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.096237128284092,
|
| 28 |
+
"grad_norm": 1.1843117475509644,
|
| 29 |
+
"learning_rate": 0.0007935972284596139,
|
| 30 |
+
"loss": 0.3736,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.128316171045456,
|
| 35 |
+
"grad_norm": 1.1524124145507812,
|
| 36 |
+
"learning_rate": 0.0007914629712794851,
|
| 37 |
+
"loss": 0.3626,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.16039521380682,
|
| 42 |
+
"grad_norm": 1.0530339479446411,
|
| 43 |
+
"learning_rate": 0.0007893244370308591,
|
| 44 |
+
"loss": 0.355,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.192474256568184,
|
| 49 |
+
"grad_norm": 1.0044286251068115,
|
| 50 |
+
"learning_rate": 0.0007871859027822331,
|
| 51 |
+
"loss": 0.3527,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.2000449106598659,
|
| 56 |
+
"eval_loss": 0.3370795249938965,
|
| 57 |
+
"eval_runtime": 6.2984,
|
| 58 |
+
"eval_samples_per_second": 79.386,
|
| 59 |
+
"eval_steps_per_second": 10.003,
|
| 60 |
+
"step": 3118
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.224553299329548,
|
| 64 |
+
"grad_norm": 1.4645978212356567,
|
| 65 |
+
"learning_rate": 0.0007850473685336071,
|
| 66 |
+
"loss": 0.3394,
|
| 67 |
+
"step": 3500
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.256632342090912,
|
| 71 |
+
"grad_norm": 1.2185771465301514,
|
| 72 |
+
"learning_rate": 0.0007829088342849811,
|
| 73 |
+
"loss": 0.3398,
|
| 74 |
+
"step": 4000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.288711384852276,
|
| 78 |
+
"grad_norm": 1.3087233304977417,
|
| 79 |
+
"learning_rate": 0.0007807703000363551,
|
| 80 |
+
"loss": 0.3399,
|
| 81 |
+
"step": 4500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.32079042761364,
|
| 85 |
+
"grad_norm": 1.411337971687317,
|
| 86 |
+
"learning_rate": 0.0007786360428562264,
|
| 87 |
+
"loss": 0.3355,
|
| 88 |
+
"step": 5000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.352869470375004,
|
| 92 |
+
"grad_norm": 1.1822813749313354,
|
| 93 |
+
"learning_rate": 0.0007764975086076004,
|
| 94 |
+
"loss": 0.3329,
|
| 95 |
+
"step": 5500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.384948513136368,
|
| 99 |
+
"grad_norm": 0.9898410439491272,
|
| 100 |
+
"learning_rate": 0.0007743632514274716,
|
| 101 |
+
"loss": 0.3311,
|
| 102 |
+
"step": 6000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.4000898213197318,
|
| 106 |
+
"eval_loss": 0.31450170278549194,
|
| 107 |
+
"eval_runtime": 9.8807,
|
| 108 |
+
"eval_samples_per_second": 50.604,
|
| 109 |
+
"eval_steps_per_second": 6.376,
|
| 110 |
+
"step": 6236
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.417027555897732,
|
| 114 |
+
"grad_norm": 0.9827210307121277,
|
| 115 |
+
"learning_rate": 0.0007722247171788456,
|
| 116 |
+
"loss": 0.3251,
|
| 117 |
+
"step": 6500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.449106598659096,
|
| 121 |
+
"grad_norm": 1.2011586427688599,
|
| 122 |
+
"learning_rate": 0.0007700861829302197,
|
| 123 |
+
"loss": 0.3271,
|
| 124 |
+
"step": 7000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.48118564142046,
|
| 128 |
+
"grad_norm": 1.3871015310287476,
|
| 129 |
+
"learning_rate": 0.0007679476486815936,
|
| 130 |
+
"loss": 0.3259,
|
| 131 |
+
"step": 7500
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.513264684181824,
|
| 135 |
+
"grad_norm": 1.1245856285095215,
|
| 136 |
+
"learning_rate": 0.0007658091144329678,
|
| 137 |
+
"loss": 0.3192,
|
| 138 |
+
"step": 8000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.545343726943188,
|
| 142 |
+
"grad_norm": 1.0883513689041138,
|
| 143 |
+
"learning_rate": 0.0007636705801843417,
|
| 144 |
+
"loss": 0.3209,
|
| 145 |
+
"step": 8500
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.577422769704552,
|
| 149 |
+
"grad_norm": 1.0555607080459595,
|
| 150 |
+
"learning_rate": 0.0007615320459357157,
|
| 151 |
+
"loss": 0.3178,
|
| 152 |
+
"step": 9000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.6001347319795978,
|
| 156 |
+
"eval_loss": 0.3085324764251709,
|
| 157 |
+
"eval_runtime": 7.9945,
|
| 158 |
+
"eval_samples_per_second": 62.543,
|
| 159 |
+
"eval_steps_per_second": 7.88,
|
| 160 |
+
"step": 9354
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.6095018124659161,
|
| 164 |
+
"grad_norm": 1.0429250001907349,
|
| 165 |
+
"learning_rate": 0.0007593935116870898,
|
| 166 |
+
"loss": 0.3169,
|
| 167 |
+
"step": 9500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.64158085522728,
|
| 171 |
+
"grad_norm": 1.2145720720291138,
|
| 172 |
+
"learning_rate": 0.0007572549774384637,
|
| 173 |
+
"loss": 0.3152,
|
| 174 |
+
"step": 10000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.673659897988644,
|
| 178 |
+
"grad_norm": 1.3464765548706055,
|
| 179 |
+
"learning_rate": 0.0007551207202583349,
|
| 180 |
+
"loss": 0.3125,
|
| 181 |
+
"step": 10500
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.705738940750008,
|
| 185 |
+
"grad_norm": 1.1744924783706665,
|
| 186 |
+
"learning_rate": 0.000752982186009709,
|
| 187 |
+
"loss": 0.3086,
|
| 188 |
+
"step": 11000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.7378179835113721,
|
| 192 |
+
"grad_norm": 1.234157919883728,
|
| 193 |
+
"learning_rate": 0.000750843651761083,
|
| 194 |
+
"loss": 0.3133,
|
| 195 |
+
"step": 11500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.769897026272736,
|
| 199 |
+
"grad_norm": 0.9248010516166687,
|
| 200 |
+
"learning_rate": 0.0007487051175124569,
|
| 201 |
+
"loss": 0.3122,
|
| 202 |
+
"step": 12000
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.8001796426394636,
|
| 206 |
+
"eval_loss": 0.3022182583808899,
|
| 207 |
+
"eval_runtime": 8.0646,
|
| 208 |
+
"eval_samples_per_second": 61.999,
|
| 209 |
+
"eval_steps_per_second": 7.812,
|
| 210 |
+
"step": 12472
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.8019760690341,
|
| 214 |
+
"grad_norm": 0.862856388092041,
|
| 215 |
+
"learning_rate": 0.000746566583263831,
|
| 216 |
+
"loss": 0.308,
|
| 217 |
+
"step": 12500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.834055111795464,
|
| 221 |
+
"grad_norm": 1.0224480628967285,
|
| 222 |
+
"learning_rate": 0.000744428049015205,
|
| 223 |
+
"loss": 0.31,
|
| 224 |
+
"step": 13000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.8661341545568281,
|
| 228 |
+
"grad_norm": 1.008195161819458,
|
| 229 |
+
"learning_rate": 0.0007422937918350763,
|
| 230 |
+
"loss": 0.3079,
|
| 231 |
+
"step": 13500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.898213197318192,
|
| 235 |
+
"grad_norm": 1.29293954372406,
|
| 236 |
+
"learning_rate": 0.0007401552575864503,
|
| 237 |
+
"loss": 0.3047,
|
| 238 |
+
"step": 14000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.930292240079556,
|
| 242 |
+
"grad_norm": 0.9913870692253113,
|
| 243 |
+
"learning_rate": 0.0007380167233378243,
|
| 244 |
+
"loss": 0.3074,
|
| 245 |
+
"step": 14500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.96237128284092,
|
| 249 |
+
"grad_norm": 1.1802239418029785,
|
| 250 |
+
"learning_rate": 0.0007358781890891983,
|
| 251 |
+
"loss": 0.3055,
|
| 252 |
+
"step": 15000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.9944503256022841,
|
| 256 |
+
"grad_norm": 1.0421093702316284,
|
| 257 |
+
"learning_rate": 0.0007337396548405722,
|
| 258 |
+
"loss": 0.3106,
|
| 259 |
+
"step": 15500
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.0001924742565682,
|
| 263 |
+
"eval_loss": 0.30451422929763794,
|
| 264 |
+
"eval_runtime": 6.8665,
|
| 265 |
+
"eval_samples_per_second": 72.817,
|
| 266 |
+
"eval_steps_per_second": 9.175,
|
| 267 |
+
"step": 15590
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.0264972893208866,
|
| 271 |
+
"grad_norm": 1.1343709230422974,
|
| 272 |
+
"learning_rate": 0.0007316011205919463,
|
| 273 |
+
"loss": 0.3028,
|
| 274 |
+
"step": 16000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.0585763320822508,
|
| 278 |
+
"grad_norm": 0.992735743522644,
|
| 279 |
+
"learning_rate": 0.0007294625863433203,
|
| 280 |
+
"loss": 0.3026,
|
| 281 |
+
"step": 16500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.0906553748436147,
|
| 285 |
+
"grad_norm": 0.9756571650505066,
|
| 286 |
+
"learning_rate": 0.0007273240520946943,
|
| 287 |
+
"loss": 0.3004,
|
| 288 |
+
"step": 17000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.1227344176049787,
|
| 292 |
+
"grad_norm": 1.005118489265442,
|
| 293 |
+
"learning_rate": 0.0007251897949145656,
|
| 294 |
+
"loss": 0.2953,
|
| 295 |
+
"step": 17500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.1548134603663427,
|
| 299 |
+
"grad_norm": 1.2004996538162231,
|
| 300 |
+
"learning_rate": 0.0007230512606659396,
|
| 301 |
+
"loss": 0.3039,
|
| 302 |
+
"step": 18000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.1868925031277067,
|
| 306 |
+
"grad_norm": 1.2973647117614746,
|
| 307 |
+
"learning_rate": 0.0007209127264173135,
|
| 308 |
+
"loss": 0.2997,
|
| 309 |
+
"step": 18500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.200237384916434,
|
| 313 |
+
"eval_loss": 0.2830166518688202,
|
| 314 |
+
"eval_runtime": 6.4164,
|
| 315 |
+
"eval_samples_per_second": 77.926,
|
| 316 |
+
"eval_steps_per_second": 9.819,
|
| 317 |
+
"step": 18708
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.2189715458890706,
|
| 321 |
+
"grad_norm": 1.2329021692276,
|
| 322 |
+
"learning_rate": 0.0007187741921686877,
|
| 323 |
+
"loss": 0.2972,
|
| 324 |
+
"step": 19000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.2510505886504346,
|
| 328 |
+
"grad_norm": 0.8207685947418213,
|
| 329 |
+
"learning_rate": 0.0007166399349885588,
|
| 330 |
+
"loss": 0.2979,
|
| 331 |
+
"step": 19500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.2831296314117986,
|
| 335 |
+
"grad_norm": 1.1549195051193237,
|
| 336 |
+
"learning_rate": 0.000714501400739933,
|
| 337 |
+
"loss": 0.2982,
|
| 338 |
+
"step": 20000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.3152086741731628,
|
| 342 |
+
"grad_norm": 1.0019187927246094,
|
| 343 |
+
"learning_rate": 0.0007123628664913069,
|
| 344 |
+
"loss": 0.2975,
|
| 345 |
+
"step": 20500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.3472877169345265,
|
| 349 |
+
"grad_norm": 1.023240327835083,
|
| 350 |
+
"learning_rate": 0.0007102243322426809,
|
| 351 |
+
"loss": 0.2957,
|
| 352 |
+
"step": 21000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.3793667596958907,
|
| 356 |
+
"grad_norm": 1.0395528078079224,
|
| 357 |
+
"learning_rate": 0.0007080900750625522,
|
| 358 |
+
"loss": 0.2957,
|
| 359 |
+
"step": 21500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.4002822955763001,
|
| 363 |
+
"eval_loss": 0.28411924839019775,
|
| 364 |
+
"eval_runtime": 8.0825,
|
| 365 |
+
"eval_samples_per_second": 61.862,
|
| 366 |
+
"eval_steps_per_second": 7.795,
|
| 367 |
+
"step": 21826
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.4114458024572547,
|
| 371 |
+
"grad_norm": 1.2371494770050049,
|
| 372 |
+
"learning_rate": 0.0007059515408139262,
|
| 373 |
+
"loss": 0.2948,
|
| 374 |
+
"step": 22000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.4435248452186187,
|
| 378 |
+
"grad_norm": 1.1509361267089844,
|
| 379 |
+
"learning_rate": 0.0007038130065653001,
|
| 380 |
+
"loss": 0.2939,
|
| 381 |
+
"step": 22500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.4756038879799827,
|
| 385 |
+
"grad_norm": 0.9148961305618286,
|
| 386 |
+
"learning_rate": 0.0007016744723166742,
|
| 387 |
+
"loss": 0.2945,
|
| 388 |
+
"step": 23000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.5076829307413466,
|
| 392 |
+
"grad_norm": 1.301382064819336,
|
| 393 |
+
"learning_rate": 0.0006995359380680482,
|
| 394 |
+
"loss": 0.2935,
|
| 395 |
+
"step": 23500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.5397619735027108,
|
| 399 |
+
"grad_norm": 1.1036344766616821,
|
| 400 |
+
"learning_rate": 0.0006974059579564167,
|
| 401 |
+
"loss": 0.2946,
|
| 402 |
+
"step": 24000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.5718410162640746,
|
| 406 |
+
"grad_norm": 1.6663960218429565,
|
| 407 |
+
"learning_rate": 0.0006952674237077907,
|
| 408 |
+
"loss": 0.2922,
|
| 409 |
+
"step": 24500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.600327206236166,
|
| 413 |
+
"eval_loss": 0.2768917977809906,
|
| 414 |
+
"eval_runtime": 6.447,
|
| 415 |
+
"eval_samples_per_second": 77.556,
|
| 416 |
+
"eval_steps_per_second": 9.772,
|
| 417 |
+
"step": 24944
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.6039200590254388,
|
| 421 |
+
"grad_norm": 1.0343741178512573,
|
| 422 |
+
"learning_rate": 0.0006931288894591647,
|
| 423 |
+
"loss": 0.2928,
|
| 424 |
+
"step": 25000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.6359991017868025,
|
| 428 |
+
"grad_norm": 1.3965007066726685,
|
| 429 |
+
"learning_rate": 0.0006909903552105388,
|
| 430 |
+
"loss": 0.2923,
|
| 431 |
+
"step": 25500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.6680781445481667,
|
| 435 |
+
"grad_norm": 1.1331425905227661,
|
| 436 |
+
"learning_rate": 0.0006888518209619127,
|
| 437 |
+
"loss": 0.2936,
|
| 438 |
+
"step": 26000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.7001571873095307,
|
| 442 |
+
"grad_norm": 1.0256651639938354,
|
| 443 |
+
"learning_rate": 0.0006867132867132868,
|
| 444 |
+
"loss": 0.2901,
|
| 445 |
+
"step": 26500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.7322362300708947,
|
| 449 |
+
"grad_norm": 1.1987167596817017,
|
| 450 |
+
"learning_rate": 0.0006845747524646608,
|
| 451 |
+
"loss": 0.2932,
|
| 452 |
+
"step": 27000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.7643152728322586,
|
| 456 |
+
"grad_norm": 0.9224876165390015,
|
| 457 |
+
"learning_rate": 0.0006824362182160348,
|
| 458 |
+
"loss": 0.2957,
|
| 459 |
+
"step": 27500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.7963943155936226,
|
| 463 |
+
"grad_norm": 1.1595081090927124,
|
| 464 |
+
"learning_rate": 0.0006802976839674088,
|
| 465 |
+
"loss": 0.2895,
|
| 466 |
+
"step": 28000
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.8003721168960318,
|
| 470 |
+
"eval_loss": 0.2766253650188446,
|
| 471 |
+
"eval_runtime": 6.995,
|
| 472 |
+
"eval_samples_per_second": 71.48,
|
| 473 |
+
"eval_steps_per_second": 9.006,
|
| 474 |
+
"step": 28062
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.8284733583549868,
|
| 478 |
+
"grad_norm": 1.0937904119491577,
|
| 479 |
+
"learning_rate": 0.0006781634267872801,
|
| 480 |
+
"loss": 0.2908,
|
| 481 |
+
"step": 28500
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.8605524011163506,
|
| 485 |
+
"grad_norm": 1.6129448413848877,
|
| 486 |
+
"learning_rate": 0.0006760291696071513,
|
| 487 |
+
"loss": 0.2865,
|
| 488 |
+
"step": 29000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.8926314438777148,
|
| 492 |
+
"grad_norm": 1.5731992721557617,
|
| 493 |
+
"learning_rate": 0.0006738906353585254,
|
| 494 |
+
"loss": 0.2865,
|
| 495 |
+
"step": 29500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.9247104866390787,
|
| 499 |
+
"grad_norm": 1.1734341382980347,
|
| 500 |
+
"learning_rate": 0.0006717521011098993,
|
| 501 |
+
"loss": 0.2858,
|
| 502 |
+
"step": 30000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.9567895294004427,
|
| 506 |
+
"grad_norm": 1.277829647064209,
|
| 507 |
+
"learning_rate": 0.0006696135668612733,
|
| 508 |
+
"loss": 0.2878,
|
| 509 |
+
"step": 30500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.9888685721618067,
|
| 513 |
+
"grad_norm": 1.2518751621246338,
|
| 514 |
+
"learning_rate": 0.0006674793096811446,
|
| 515 |
+
"loss": 0.2847,
|
| 516 |
+
"step": 31000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.0003849485131364,
|
| 520 |
+
"eval_loss": 0.2660098075866699,
|
| 521 |
+
"eval_runtime": 8.1469,
|
| 522 |
+
"eval_samples_per_second": 61.373,
|
| 523 |
+
"eval_steps_per_second": 7.733,
|
| 524 |
+
"step": 31180
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.0209155358804094,
|
| 528 |
+
"grad_norm": 1.0406543016433716,
|
| 529 |
+
"learning_rate": 0.0006653407754325186,
|
| 530 |
+
"loss": 0.2821,
|
| 531 |
+
"step": 31500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.052994578641773,
|
| 535 |
+
"grad_norm": 1.1324297189712524,
|
| 536 |
+
"learning_rate": 0.0006632022411838926,
|
| 537 |
+
"loss": 0.2848,
|
| 538 |
+
"step": 32000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.0850736214031373,
|
| 542 |
+
"grad_norm": 1.0970991849899292,
|
| 543 |
+
"learning_rate": 0.0006610637069352665,
|
| 544 |
+
"loss": 0.2815,
|
| 545 |
+
"step": 32500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.1171526641645015,
|
| 549 |
+
"grad_norm": 1.0462357997894287,
|
| 550 |
+
"learning_rate": 0.0006589251726866407,
|
| 551 |
+
"loss": 0.2825,
|
| 552 |
+
"step": 33000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.1492317069258653,
|
| 556 |
+
"grad_norm": 1.122344732284546,
|
| 557 |
+
"learning_rate": 0.0006567866384380146,
|
| 558 |
+
"loss": 0.2816,
|
| 559 |
+
"step": 33500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.1813107496872295,
|
| 563 |
+
"grad_norm": 1.108782410621643,
|
| 564 |
+
"learning_rate": 0.0006546481041893886,
|
| 565 |
+
"loss": 0.2826,
|
| 566 |
+
"step": 34000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.2004298591730023,
|
| 570 |
+
"eval_loss": 0.2733038365840912,
|
| 571 |
+
"eval_runtime": 7.489,
|
| 572 |
+
"eval_samples_per_second": 66.765,
|
| 573 |
+
"eval_steps_per_second": 8.412,
|
| 574 |
+
"step": 34298
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.2133897924485932,
|
| 578 |
+
"grad_norm": 1.092699646949768,
|
| 579 |
+
"learning_rate": 0.0006525095699407627,
|
| 580 |
+
"loss": 0.2836,
|
| 581 |
+
"step": 34500
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.2454688352099574,
|
| 585 |
+
"grad_norm": 1.0987275838851929,
|
| 586 |
+
"learning_rate": 0.0006503753127606339,
|
| 587 |
+
"loss": 0.2779,
|
| 588 |
+
"step": 35000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.277547877971321,
|
| 592 |
+
"grad_norm": 1.1260478496551514,
|
| 593 |
+
"learning_rate": 0.0006482367785120078,
|
| 594 |
+
"loss": 0.2788,
|
| 595 |
+
"step": 35500
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.3096269207326854,
|
| 599 |
+
"grad_norm": 1.2035844326019287,
|
| 600 |
+
"learning_rate": 0.0006460982442633819,
|
| 601 |
+
"loss": 0.284,
|
| 602 |
+
"step": 36000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.341705963494049,
|
| 606 |
+
"grad_norm": 1.0569308996200562,
|
| 607 |
+
"learning_rate": 0.0006439597100147559,
|
| 608 |
+
"loss": 0.2812,
|
| 609 |
+
"step": 36500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.3737850062554133,
|
| 613 |
+
"grad_norm": 0.8856455683708191,
|
| 614 |
+
"learning_rate": 0.0006418254528346272,
|
| 615 |
+
"loss": 0.2767,
|
| 616 |
+
"step": 37000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.400474769832868,
|
| 620 |
+
"eval_loss": 0.2658798098564148,
|
| 621 |
+
"eval_runtime": 8.0192,
|
| 622 |
+
"eval_samples_per_second": 62.35,
|
| 623 |
+
"eval_steps_per_second": 7.856,
|
| 624 |
+
"step": 37416
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.4058640490167775,
|
| 628 |
+
"grad_norm": 0.9563117027282715,
|
| 629 |
+
"learning_rate": 0.0006396911956544984,
|
| 630 |
+
"loss": 0.2787,
|
| 631 |
+
"step": 37500
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.4379430917781413,
|
| 635 |
+
"grad_norm": 0.9825711250305176,
|
| 636 |
+
"learning_rate": 0.0006375526614058725,
|
| 637 |
+
"loss": 0.2775,
|
| 638 |
+
"step": 38000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.4700221345395055,
|
| 642 |
+
"grad_norm": 1.1553630828857422,
|
| 643 |
+
"learning_rate": 0.0006354141271572465,
|
| 644 |
+
"loss": 0.2779,
|
| 645 |
+
"step": 38500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.5021011773008692,
|
| 649 |
+
"grad_norm": 1.1160862445831299,
|
| 650 |
+
"learning_rate": 0.0006332755929086204,
|
| 651 |
+
"loss": 0.2819,
|
| 652 |
+
"step": 39000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.5341802200622334,
|
| 656 |
+
"grad_norm": 1.2663159370422363,
|
| 657 |
+
"learning_rate": 0.0006311370586599945,
|
| 658 |
+
"loss": 0.2797,
|
| 659 |
+
"step": 39500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.566259262823597,
|
| 663 |
+
"grad_norm": 1.028053641319275,
|
| 664 |
+
"learning_rate": 0.0006289985244113685,
|
| 665 |
+
"loss": 0.2776,
|
| 666 |
+
"step": 40000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 2.5983383055849614,
|
| 670 |
+
"grad_norm": 1.0482547283172607,
|
| 671 |
+
"learning_rate": 0.0006268642672312397,
|
| 672 |
+
"loss": 0.2737,
|
| 673 |
+
"step": 40500
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 2.600519680492734,
|
| 677 |
+
"eval_loss": 0.26375094056129456,
|
| 678 |
+
"eval_runtime": 7.2264,
|
| 679 |
+
"eval_samples_per_second": 69.19,
|
| 680 |
+
"eval_steps_per_second": 8.718,
|
| 681 |
+
"step": 40534
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.6304173483463256,
|
| 685 |
+
"grad_norm": 1.0435316562652588,
|
| 686 |
+
"learning_rate": 0.0006247257329826138,
|
| 687 |
+
"loss": 0.2783,
|
| 688 |
+
"step": 41000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.6624963911076893,
|
| 692 |
+
"grad_norm": 0.866886556148529,
|
| 693 |
+
"learning_rate": 0.0006225871987339878,
|
| 694 |
+
"loss": 0.2738,
|
| 695 |
+
"step": 41500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.694575433869053,
|
| 699 |
+
"grad_norm": 1.069162368774414,
|
| 700 |
+
"learning_rate": 0.0006204486644853617,
|
| 701 |
+
"loss": 0.2783,
|
| 702 |
+
"step": 42000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.7266544766304173,
|
| 706 |
+
"grad_norm": 1.450871229171753,
|
| 707 |
+
"learning_rate": 0.0006183101302367357,
|
| 708 |
+
"loss": 0.275,
|
| 709 |
+
"step": 42500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.7587335193917815,
|
| 713 |
+
"grad_norm": 1.0573506355285645,
|
| 714 |
+
"learning_rate": 0.000616175873056607,
|
| 715 |
+
"loss": 0.2762,
|
| 716 |
+
"step": 43000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.790812562153145,
|
| 720 |
+
"grad_norm": 1.1295759677886963,
|
| 721 |
+
"learning_rate": 0.000614037338807981,
|
| 722 |
+
"loss": 0.2734,
|
| 723 |
+
"step": 43500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.8005645911526003,
|
| 727 |
+
"eval_loss": 0.26422494649887085,
|
| 728 |
+
"eval_runtime": 8.0132,
|
| 729 |
+
"eval_samples_per_second": 62.397,
|
| 730 |
+
"eval_steps_per_second": 7.862,
|
| 731 |
+
"step": 43652
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.8228916049145094,
|
| 735 |
+
"grad_norm": 1.1608061790466309,
|
| 736 |
+
"learning_rate": 0.000611898804559355,
|
| 737 |
+
"loss": 0.272,
|
| 738 |
+
"step": 44000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.8549706476758736,
|
| 742 |
+
"grad_norm": 1.2949804067611694,
|
| 743 |
+
"learning_rate": 0.000609760270310729,
|
| 744 |
+
"loss": 0.272,
|
| 745 |
+
"step": 44500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.8870496904372374,
|
| 749 |
+
"grad_norm": 0.9073989391326904,
|
| 750 |
+
"learning_rate": 0.0006076217360621031,
|
| 751 |
+
"loss": 0.2744,
|
| 752 |
+
"step": 45000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.919128733198601,
|
| 756 |
+
"grad_norm": 0.8703099489212036,
|
| 757 |
+
"learning_rate": 0.0006054874788819743,
|
| 758 |
+
"loss": 0.2762,
|
| 759 |
+
"step": 45500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.9512077759599653,
|
| 763 |
+
"grad_norm": 1.0385627746582031,
|
| 764 |
+
"learning_rate": 0.0006033489446333484,
|
| 765 |
+
"loss": 0.2732,
|
| 766 |
+
"step": 46000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.9832868187213295,
|
| 770 |
+
"grad_norm": 1.1464110612869263,
|
| 771 |
+
"learning_rate": 0.0006012104103847223,
|
| 772 |
+
"loss": 0.2701,
|
| 773 |
+
"step": 46500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.0005774227697044,
|
| 777 |
+
"eval_loss": 0.2622199058532715,
|
| 778 |
+
"eval_runtime": 6.3897,
|
| 779 |
+
"eval_samples_per_second": 78.251,
|
| 780 |
+
"eval_steps_per_second": 9.86,
|
| 781 |
+
"step": 46770
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 3.015333782439932,
|
| 785 |
+
"grad_norm": 1.2512695789337158,
|
| 786 |
+
"learning_rate": 0.0005990718761360964,
|
| 787 |
+
"loss": 0.2697,
|
| 788 |
+
"step": 47000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.047412825201296,
|
| 792 |
+
"grad_norm": 0.7882702946662903,
|
| 793 |
+
"learning_rate": 0.0005969376189559676,
|
| 794 |
+
"loss": 0.2685,
|
| 795 |
+
"step": 47500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 3.07949186796266,
|
| 799 |
+
"grad_norm": 1.282387614250183,
|
| 800 |
+
"learning_rate": 0.0005947990847073416,
|
| 801 |
+
"loss": 0.2674,
|
| 802 |
+
"step": 48000
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 3.111570910724024,
|
| 806 |
+
"grad_norm": 1.4220795631408691,
|
| 807 |
+
"learning_rate": 0.0005926605504587157,
|
| 808 |
+
"loss": 0.2676,
|
| 809 |
+
"step": 48500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.143649953485388,
|
| 813 |
+
"grad_norm": 1.0576750040054321,
|
| 814 |
+
"learning_rate": 0.0005905220162100896,
|
| 815 |
+
"loss": 0.269,
|
| 816 |
+
"step": 49000
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.175728996246752,
|
| 820 |
+
"grad_norm": 1.0533617734909058,
|
| 821 |
+
"learning_rate": 0.0005883834819614636,
|
| 822 |
+
"loss": 0.2629,
|
| 823 |
+
"step": 49500
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 3.2006223334295703,
|
| 827 |
+
"eval_loss": 0.2548312246799469,
|
| 828 |
+
"eval_runtime": 6.5962,
|
| 829 |
+
"eval_samples_per_second": 75.802,
|
| 830 |
+
"eval_steps_per_second": 9.551,
|
| 831 |
+
"step": 49888
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 3.207808039008116,
|
| 835 |
+
"grad_norm": 1.1989775896072388,
|
| 836 |
+
"learning_rate": 0.0005862449477128377,
|
| 837 |
+
"loss": 0.2666,
|
| 838 |
+
"step": 50000
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 3.23988708176948,
|
| 842 |
+
"grad_norm": 1.0356203317642212,
|
| 843 |
+
"learning_rate": 0.0005841064134642117,
|
| 844 |
+
"loss": 0.2622,
|
| 845 |
+
"step": 50500
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 3.2719661245308442,
|
| 849 |
+
"grad_norm": 1.0133503675460815,
|
| 850 |
+
"learning_rate": 0.0005819721562840828,
|
| 851 |
+
"loss": 0.2671,
|
| 852 |
+
"step": 51000
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 3.304045167292208,
|
| 856 |
+
"grad_norm": 1.1607108116149902,
|
| 857 |
+
"learning_rate": 0.000579833622035457,
|
| 858 |
+
"loss": 0.2633,
|
| 859 |
+
"step": 51500
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 3.336124210053572,
|
| 863 |
+
"grad_norm": 1.0809621810913086,
|
| 864 |
+
"learning_rate": 0.0005776950877868309,
|
| 865 |
+
"loss": 0.267,
|
| 866 |
+
"step": 52000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.368203252814936,
|
| 870 |
+
"grad_norm": 1.1140522956848145,
|
| 871 |
+
"learning_rate": 0.0005755565535382049,
|
| 872 |
+
"loss": 0.2655,
|
| 873 |
+
"step": 52500
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.4002822955763,
|
| 877 |
+
"grad_norm": 1.4667320251464844,
|
| 878 |
+
"learning_rate": 0.0005734222963580762,
|
| 879 |
+
"loss": 0.2652,
|
| 880 |
+
"step": 53000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.4006672440894365,
|
| 884 |
+
"eval_loss": 0.25107353925704956,
|
| 885 |
+
"eval_runtime": 8.1009,
|
| 886 |
+
"eval_samples_per_second": 61.721,
|
| 887 |
+
"eval_steps_per_second": 7.777,
|
| 888 |
+
"step": 53006
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 3.432361338337664,
|
| 892 |
+
"grad_norm": 1.0906621217727661,
|
| 893 |
+
"learning_rate": 0.0005712837621094502,
|
| 894 |
+
"loss": 0.2633,
|
| 895 |
+
"step": 53500
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 3.464440381099028,
|
| 899 |
+
"grad_norm": 1.7066080570220947,
|
| 900 |
+
"learning_rate": 0.0005691452278608242,
|
| 901 |
+
"loss": 0.2624,
|
| 902 |
+
"step": 54000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 3.496519423860392,
|
| 906 |
+
"grad_norm": 1.1421736478805542,
|
| 907 |
+
"learning_rate": 0.0005670066936121983,
|
| 908 |
+
"loss": 0.267,
|
| 909 |
+
"step": 54500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 3.528598466621756,
|
| 913 |
+
"grad_norm": 0.9186555743217468,
|
| 914 |
+
"learning_rate": 0.0005648681593635722,
|
| 915 |
+
"loss": 0.2646,
|
| 916 |
+
"step": 55000
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 3.5606775093831198,
|
| 920 |
+
"grad_norm": 0.8647829294204712,
|
| 921 |
+
"learning_rate": 0.0005627339021834436,
|
| 922 |
+
"loss": 0.2614,
|
| 923 |
+
"step": 55500
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.592756552144484,
|
| 927 |
+
"grad_norm": 0.9938694834709167,
|
| 928 |
+
"learning_rate": 0.0005605953679348175,
|
| 929 |
+
"loss": 0.263,
|
| 930 |
+
"step": 56000
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 3.6007121547493024,
|
| 934 |
+
"eval_loss": 0.2563716173171997,
|
| 935 |
+
"eval_runtime": 6.467,
|
| 936 |
+
"eval_samples_per_second": 77.315,
|
| 937 |
+
"eval_steps_per_second": 9.742,
|
| 938 |
+
"step": 56124
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.624835594905848,
|
| 942 |
+
"grad_norm": 0.8723744750022888,
|
| 943 |
+
"learning_rate": 0.0005584568336861915,
|
| 944 |
+
"loss": 0.2612,
|
| 945 |
+
"step": 56500
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 3.656914637667212,
|
| 949 |
+
"grad_norm": 1.0959194898605347,
|
| 950 |
+
"learning_rate": 0.0005563182994375655,
|
| 951 |
+
"loss": 0.2611,
|
| 952 |
+
"step": 57000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.688993680428576,
|
| 956 |
+
"grad_norm": 1.2405571937561035,
|
| 957 |
+
"learning_rate": 0.0005541797651889395,
|
| 958 |
+
"loss": 0.2635,
|
| 959 |
+
"step": 57500
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 3.72107272318994,
|
| 963 |
+
"grad_norm": 1.137342929840088,
|
| 964 |
+
"learning_rate": 0.0005520412309403136,
|
| 965 |
+
"loss": 0.2595,
|
| 966 |
+
"step": 58000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.753151765951304,
|
| 970 |
+
"grad_norm": 0.8755650520324707,
|
| 971 |
+
"learning_rate": 0.0005499026966916875,
|
| 972 |
+
"loss": 0.2619,
|
| 973 |
+
"step": 58500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 3.785230808712668,
|
| 977 |
+
"grad_norm": 1.2968310117721558,
|
| 978 |
+
"learning_rate": 0.0005477641624430616,
|
| 979 |
+
"loss": 0.2612,
|
| 980 |
+
"step": 59000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.8007570654091682,
|
| 984 |
+
"eval_loss": 0.2506495714187622,
|
| 985 |
+
"eval_runtime": 8.1115,
|
| 986 |
+
"eval_samples_per_second": 61.641,
|
| 987 |
+
"eval_steps_per_second": 7.767,
|
| 988 |
+
"step": 59242
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 3.817309851474032,
|
| 992 |
+
"grad_norm": 0.9842492938041687,
|
| 993 |
+
"learning_rate": 0.0005456299052629328,
|
| 994 |
+
"loss": 0.2624,
|
| 995 |
+
"step": 59500
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 3.849388894235396,
|
| 999 |
+
"grad_norm": 0.8897719979286194,
|
| 1000 |
+
"learning_rate": 0.0005434913710143068,
|
| 1001 |
+
"loss": 0.2573,
|
| 1002 |
+
"step": 60000
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 3.88146793699676,
|
| 1006 |
+
"grad_norm": 0.9902140498161316,
|
| 1007 |
+
"learning_rate": 0.0005413528367656809,
|
| 1008 |
+
"loss": 0.2624,
|
| 1009 |
+
"step": 60500
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 3.913546979758124,
|
| 1013 |
+
"grad_norm": 0.9460390210151672,
|
| 1014 |
+
"learning_rate": 0.0005392185795855521,
|
| 1015 |
+
"loss": 0.2582,
|
| 1016 |
+
"step": 61000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.945626022519488,
|
| 1020 |
+
"grad_norm": 1.1403892040252686,
|
| 1021 |
+
"learning_rate": 0.0005370800453369261,
|
| 1022 |
+
"loss": 0.2627,
|
| 1023 |
+
"step": 61500
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 3.977705065280852,
|
| 1027 |
+
"grad_norm": 0.987301766872406,
|
| 1028 |
+
"learning_rate": 0.0005349415110883001,
|
| 1029 |
+
"loss": 0.2616,
|
| 1030 |
+
"step": 62000
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 4.000769897026273,
|
| 1034 |
+
"eval_loss": 0.2439550757408142,
|
| 1035 |
+
"eval_runtime": 7.3235,
|
| 1036 |
+
"eval_samples_per_second": 68.274,
|
| 1037 |
+
"eval_steps_per_second": 8.602,
|
| 1038 |
+
"step": 62360
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 4.009752028999455,
|
| 1042 |
+
"grad_norm": 0.9634618163108826,
|
| 1043 |
+
"learning_rate": 0.0005328029768396741,
|
| 1044 |
+
"loss": 0.2522,
|
| 1045 |
+
"step": 62500
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 4.041831071760819,
|
| 1049 |
+
"grad_norm": 1.0599830150604248,
|
| 1050 |
+
"learning_rate": 0.0005306687196595454,
|
| 1051 |
+
"loss": 0.2548,
|
| 1052 |
+
"step": 63000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 4.0739101145221825,
|
| 1056 |
+
"grad_norm": 1.1028203964233398,
|
| 1057 |
+
"learning_rate": 0.0005285301854109194,
|
| 1058 |
+
"loss": 0.2529,
|
| 1059 |
+
"step": 63500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 4.105989157283546,
|
| 1063 |
+
"grad_norm": 1.1508251428604126,
|
| 1064 |
+
"learning_rate": 0.0005263916511622933,
|
| 1065 |
+
"loss": 0.2539,
|
| 1066 |
+
"step": 64000
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 4.138068200044911,
|
| 1070 |
+
"grad_norm": 1.0701543092727661,
|
| 1071 |
+
"learning_rate": 0.0005242531169136675,
|
| 1072 |
+
"loss": 0.2502,
|
| 1073 |
+
"step": 64500
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 4.170147242806275,
|
| 1077 |
+
"grad_norm": 1.0984095335006714,
|
| 1078 |
+
"learning_rate": 0.0005221145826650414,
|
| 1079 |
+
"loss": 0.2574,
|
| 1080 |
+
"step": 65000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 4.200814807686139,
|
| 1084 |
+
"eval_loss": 0.24038133025169373,
|
| 1085 |
+
"eval_runtime": 6.2912,
|
| 1086 |
+
"eval_samples_per_second": 79.476,
|
| 1087 |
+
"eval_steps_per_second": 10.014,
|
| 1088 |
+
"step": 65478
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.202226285567638,
|
| 1092 |
+
"grad_norm": 0.9908430576324463,
|
| 1093 |
+
"learning_rate": 0.0005199803254849126,
|
| 1094 |
+
"loss": 0.2564,
|
| 1095 |
+
"step": 65500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 4.234305328329003,
|
| 1099 |
+
"grad_norm": 1.0797010660171509,
|
| 1100 |
+
"learning_rate": 0.0005178417912362867,
|
| 1101 |
+
"loss": 0.2568,
|
| 1102 |
+
"step": 66000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 4.266384371090367,
|
| 1106 |
+
"grad_norm": 1.3110967874526978,
|
| 1107 |
+
"learning_rate": 0.0005157032569876607,
|
| 1108 |
+
"loss": 0.2546,
|
| 1109 |
+
"step": 66500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 4.298463413851731,
|
| 1113 |
+
"grad_norm": 1.22694993019104,
|
| 1114 |
+
"learning_rate": 0.0005135647227390347,
|
| 1115 |
+
"loss": 0.253,
|
| 1116 |
+
"step": 67000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.330542456613094,
|
| 1120 |
+
"grad_norm": 1.146044373512268,
|
| 1121 |
+
"learning_rate": 0.000511430465558906,
|
| 1122 |
+
"loss": 0.2529,
|
| 1123 |
+
"step": 67500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 4.362621499374459,
|
| 1127 |
+
"grad_norm": 1.0950199365615845,
|
| 1128 |
+
"learning_rate": 0.0005092919313102799,
|
| 1129 |
+
"loss": 0.2506,
|
| 1130 |
+
"step": 68000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.394700542135823,
|
| 1134 |
+
"grad_norm": 1.1739941835403442,
|
| 1135 |
+
"learning_rate": 0.0005071533970616539,
|
| 1136 |
+
"loss": 0.2501,
|
| 1137 |
+
"step": 68500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 4.4008597183460045,
|
| 1141 |
+
"eval_loss": 0.24005259573459625,
|
| 1142 |
+
"eval_runtime": 7.6188,
|
| 1143 |
+
"eval_samples_per_second": 65.627,
|
| 1144 |
+
"eval_steps_per_second": 8.269,
|
| 1145 |
+
"step": 68596
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.4267795848971865,
|
| 1149 |
+
"grad_norm": 1.3007426261901855,
|
| 1150 |
+
"learning_rate": 0.000505014862813028,
|
| 1151 |
+
"loss": 0.2507,
|
| 1152 |
+
"step": 69000
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.45885862765855,
|
| 1156 |
+
"grad_norm": 1.0202151536941528,
|
| 1157 |
+
"learning_rate": 0.0005028763285644019,
|
| 1158 |
+
"loss": 0.2535,
|
| 1159 |
+
"step": 69500
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 4.490937670419915,
|
| 1163 |
+
"grad_norm": 1.5328317880630493,
|
| 1164 |
+
"learning_rate": 0.000500737794315776,
|
| 1165 |
+
"loss": 0.2522,
|
| 1166 |
+
"step": 70000
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 4.523016713181279,
|
| 1170 |
+
"grad_norm": 1.0239914655685425,
|
| 1171 |
+
"learning_rate": 0.0004986035371356472,
|
| 1172 |
+
"loss": 0.2496,
|
| 1173 |
+
"step": 70500
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 4.555095755942642,
|
| 1177 |
+
"grad_norm": 0.9700740575790405,
|
| 1178 |
+
"learning_rate": 0.0004964650028870213,
|
| 1179 |
+
"loss": 0.2512,
|
| 1180 |
+
"step": 71000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 4.587174798704007,
|
| 1184 |
+
"grad_norm": 1.2554644346237183,
|
| 1185 |
+
"learning_rate": 0.0004943264686383952,
|
| 1186 |
+
"loss": 0.2506,
|
| 1187 |
+
"step": 71500
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 4.60090462900587,
|
| 1191 |
+
"eval_loss": 0.24138595163822174,
|
| 1192 |
+
"eval_runtime": 8.1086,
|
| 1193 |
+
"eval_samples_per_second": 61.663,
|
| 1194 |
+
"eval_steps_per_second": 7.77,
|
| 1195 |
+
"step": 71714
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 4.619253841465371,
|
| 1199 |
+
"grad_norm": 1.5016344785690308,
|
| 1200 |
+
"learning_rate": 0.0004921879343897693,
|
| 1201 |
+
"loss": 0.2471,
|
| 1202 |
+
"step": 72000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 4.6513328842267345,
|
| 1206 |
+
"grad_norm": 1.251976490020752,
|
| 1207 |
+
"learning_rate": 0.0004900494001411433,
|
| 1208 |
+
"loss": 0.2531,
|
| 1209 |
+
"step": 72500
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 4.683411926988098,
|
| 1213 |
+
"grad_norm": 1.0139933824539185,
|
| 1214 |
+
"learning_rate": 0.0004879151429610145,
|
| 1215 |
+
"loss": 0.2488,
|
| 1216 |
+
"step": 73000
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 4.715490969749463,
|
| 1220 |
+
"grad_norm": 0.9058252573013306,
|
| 1221 |
+
"learning_rate": 0.0004857766087123886,
|
| 1222 |
+
"loss": 0.2478,
|
| 1223 |
+
"step": 73500
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 4.747570012510827,
|
| 1227 |
+
"grad_norm": 0.8362458944320679,
|
| 1228 |
+
"learning_rate": 0.00048363807446376257,
|
| 1229 |
+
"loss": 0.2495,
|
| 1230 |
+
"step": 74000
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 4.77964905527219,
|
| 1234 |
+
"grad_norm": 0.996514081954956,
|
| 1235 |
+
"learning_rate": 0.00048149954021513655,
|
| 1236 |
+
"loss": 0.251,
|
| 1237 |
+
"step": 74500
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 4.800949539665736,
|
| 1241 |
+
"eval_loss": 0.23780158162117004,
|
| 1242 |
+
"eval_runtime": 6.3001,
|
| 1243 |
+
"eval_samples_per_second": 79.364,
|
| 1244 |
+
"eval_steps_per_second": 10.0,
|
| 1245 |
+
"step": 74832
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 4.811728098033555,
|
| 1249 |
+
"grad_norm": 1.115113377571106,
|
| 1250 |
+
"learning_rate": 0.00047936528303500785,
|
| 1251 |
+
"loss": 0.2477,
|
| 1252 |
+
"step": 75000
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 4.843807140794919,
|
| 1256 |
+
"grad_norm": 1.2068469524383545,
|
| 1257 |
+
"learning_rate": 0.00047722674878638183,
|
| 1258 |
+
"loss": 0.2462,
|
| 1259 |
+
"step": 75500
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 4.875886183556283,
|
| 1263 |
+
"grad_norm": 1.0453870296478271,
|
| 1264 |
+
"learning_rate": 0.0004750882145377558,
|
| 1265 |
+
"loss": 0.2456,
|
| 1266 |
+
"step": 76000
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 4.907965226317646,
|
| 1270 |
+
"grad_norm": 1.0999488830566406,
|
| 1271 |
+
"learning_rate": 0.0004729496802891299,
|
| 1272 |
+
"loss": 0.2492,
|
| 1273 |
+
"step": 76500
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 4.940044269079011,
|
| 1277 |
+
"grad_norm": 0.8874688148498535,
|
| 1278 |
+
"learning_rate": 0.00047081114604050387,
|
| 1279 |
+
"loss": 0.2467,
|
| 1280 |
+
"step": 77000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 4.972123311840375,
|
| 1284 |
+
"grad_norm": 1.060391902923584,
|
| 1285 |
+
"learning_rate": 0.0004686726117918779,
|
| 1286 |
+
"loss": 0.2456,
|
| 1287 |
+
"step": 77500
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 5.000962371282841,
|
| 1291 |
+
"eval_loss": 0.2328067272901535,
|
| 1292 |
+
"eval_runtime": 6.3234,
|
| 1293 |
+
"eval_samples_per_second": 79.071,
|
| 1294 |
+
"eval_steps_per_second": 9.963,
|
| 1295 |
+
"step": 77950
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 5.004170275558978,
|
| 1299 |
+
"grad_norm": 1.7267987728118896,
|
| 1300 |
+
"learning_rate": 0.00046653835461174916,
|
| 1301 |
+
"loss": 0.2407,
|
| 1302 |
+
"step": 78000
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 5.036249318320341,
|
| 1306 |
+
"grad_norm": 0.986152172088623,
|
| 1307 |
+
"learning_rate": 0.00046439982036312313,
|
| 1308 |
+
"loss": 0.2428,
|
| 1309 |
+
"step": 78500
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 5.068328361081705,
|
| 1313 |
+
"grad_norm": 1.4283899068832397,
|
| 1314 |
+
"learning_rate": 0.00046226128611449716,
|
| 1315 |
+
"loss": 0.2451,
|
| 1316 |
+
"step": 79000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 5.100407403843069,
|
| 1320 |
+
"grad_norm": 1.2393862009048462,
|
| 1321 |
+
"learning_rate": 0.00046012275186587114,
|
| 1322 |
+
"loss": 0.2414,
|
| 1323 |
+
"step": 79500
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 5.1324864466044335,
|
| 1327 |
+
"grad_norm": 0.9746513962745667,
|
| 1328 |
+
"learning_rate": 0.00045798849468574245,
|
| 1329 |
+
"loss": 0.2421,
|
| 1330 |
+
"step": 80000
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 5.164565489365797,
|
| 1334 |
+
"grad_norm": 1.897164225578308,
|
| 1335 |
+
"learning_rate": 0.0004558499604371164,
|
| 1336 |
+
"loss": 0.2408,
|
| 1337 |
+
"step": 80500
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 5.196644532127161,
|
| 1341 |
+
"grad_norm": 1.1321191787719727,
|
| 1342 |
+
"learning_rate": 0.0004537114261884904,
|
| 1343 |
+
"loss": 0.2418,
|
| 1344 |
+
"step": 81000
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 5.201007281942707,
|
| 1348 |
+
"eval_loss": 0.237562894821167,
|
| 1349 |
+
"eval_runtime": 6.3075,
|
| 1350 |
+
"eval_samples_per_second": 79.271,
|
| 1351 |
+
"eval_steps_per_second": 9.988,
|
| 1352 |
+
"step": 81068
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 5.228723574888526,
|
| 1356 |
+
"grad_norm": 1.1551389694213867,
|
| 1357 |
+
"learning_rate": 0.0004515728919398645,
|
| 1358 |
+
"loss": 0.2417,
|
| 1359 |
+
"step": 81500
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 5.260802617649889,
|
| 1363 |
+
"grad_norm": 1.0562560558319092,
|
| 1364 |
+
"learning_rate": 0.00044943435769123847,
|
| 1365 |
+
"loss": 0.241,
|
| 1366 |
+
"step": 82000
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 5.292881660411253,
|
| 1370 |
+
"grad_norm": 1.0487314462661743,
|
| 1371 |
+
"learning_rate": 0.00044730010051110967,
|
| 1372 |
+
"loss": 0.2413,
|
| 1373 |
+
"step": 82500
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 5.324960703172617,
|
| 1377 |
+
"grad_norm": 1.2570559978485107,
|
| 1378 |
+
"learning_rate": 0.00044516156626248375,
|
| 1379 |
+
"loss": 0.2405,
|
| 1380 |
+
"step": 83000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 5.357039745933982,
|
| 1384 |
+
"grad_norm": 1.0819013118743896,
|
| 1385 |
+
"learning_rate": 0.00044302303201385773,
|
| 1386 |
+
"loss": 0.2414,
|
| 1387 |
+
"step": 83500
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 5.389118788695345,
|
| 1391 |
+
"grad_norm": 0.9494850039482117,
|
| 1392 |
+
"learning_rate": 0.00044088449776523176,
|
| 1393 |
+
"loss": 0.2395,
|
| 1394 |
+
"step": 84000
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 5.401052192602573,
|
| 1398 |
+
"eval_loss": 0.2342357486486435,
|
| 1399 |
+
"eval_runtime": 6.4142,
|
| 1400 |
+
"eval_samples_per_second": 77.952,
|
| 1401 |
+
"eval_steps_per_second": 9.822,
|
| 1402 |
+
"step": 84186
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 5.421197831456709,
|
| 1406 |
+
"grad_norm": 1.060643196105957,
|
| 1407 |
+
"learning_rate": 0.00043874596351660574,
|
| 1408 |
+
"loss": 0.2388,
|
| 1409 |
+
"step": 84500
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 5.453276874218074,
|
| 1413 |
+
"grad_norm": 1.2068923711776733,
|
| 1414 |
+
"learning_rate": 0.0004366074292679797,
|
| 1415 |
+
"loss": 0.2387,
|
| 1416 |
+
"step": 85000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 5.4853559169794375,
|
| 1420 |
+
"grad_norm": 1.0651592016220093,
|
| 1421 |
+
"learning_rate": 0.000434473172087851,
|
| 1422 |
+
"loss": 0.2406,
|
| 1423 |
+
"step": 85500
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 5.517434959740801,
|
| 1427 |
+
"grad_norm": 0.8992927670478821,
|
| 1428 |
+
"learning_rate": 0.000432334637839225,
|
| 1429 |
+
"loss": 0.2365,
|
| 1430 |
+
"step": 86000
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 5.549514002502165,
|
| 1434 |
+
"grad_norm": 1.0418347120285034,
|
| 1435 |
+
"learning_rate": 0.000430196103590599,
|
| 1436 |
+
"loss": 0.2381,
|
| 1437 |
+
"step": 86500
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 5.58159304526353,
|
| 1441 |
+
"grad_norm": 1.3282594680786133,
|
| 1442 |
+
"learning_rate": 0.00042805756934197306,
|
| 1443 |
+
"loss": 0.2364,
|
| 1444 |
+
"step": 87000
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 5.601097103262439,
|
| 1448 |
+
"eval_loss": 0.22406485676765442,
|
| 1449 |
+
"eval_runtime": 8.0745,
|
| 1450 |
+
"eval_samples_per_second": 61.923,
|
| 1451 |
+
"eval_steps_per_second": 7.802,
|
| 1452 |
+
"step": 87304
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 5.613672088024893,
|
| 1456 |
+
"grad_norm": 1.2747199535369873,
|
| 1457 |
+
"learning_rate": 0.00042592331216184426,
|
| 1458 |
+
"loss": 0.2379,
|
| 1459 |
+
"step": 87500
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 5.645751130786257,
|
| 1463 |
+
"grad_norm": 0.9160233736038208,
|
| 1464 |
+
"learning_rate": 0.00042378477791321835,
|
| 1465 |
+
"loss": 0.235,
|
| 1466 |
+
"step": 88000
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 5.677830173547621,
|
| 1470 |
+
"grad_norm": 1.2351807355880737,
|
| 1471 |
+
"learning_rate": 0.0004216462436645923,
|
| 1472 |
+
"loss": 0.2371,
|
| 1473 |
+
"step": 88500
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 5.7099092163089855,
|
| 1477 |
+
"grad_norm": 0.9699601531028748,
|
| 1478 |
+
"learning_rate": 0.0004195077094159663,
|
| 1479 |
+
"loss": 0.2359,
|
| 1480 |
+
"step": 89000
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 5.741988259070349,
|
| 1484 |
+
"grad_norm": 0.8815991282463074,
|
| 1485 |
+
"learning_rate": 0.00041736917516734033,
|
| 1486 |
+
"loss": 0.2362,
|
| 1487 |
+
"step": 89500
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 5.774067301831713,
|
| 1491 |
+
"grad_norm": 0.9497590661048889,
|
| 1492 |
+
"learning_rate": 0.0004152306409187143,
|
| 1493 |
+
"loss": 0.2334,
|
| 1494 |
+
"step": 90000
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 5.801142013922305,
|
| 1498 |
+
"eval_loss": 0.22982336580753326,
|
| 1499 |
+
"eval_runtime": 6.3324,
|
| 1500 |
+
"eval_samples_per_second": 78.959,
|
| 1501 |
+
"eval_steps_per_second": 9.949,
|
| 1502 |
+
"step": 90422
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 5.806146344593078,
|
| 1506 |
+
"grad_norm": 0.9176979660987854,
|
| 1507 |
+
"learning_rate": 0.0004130921066700883,
|
| 1508 |
+
"loss": 0.2342,
|
| 1509 |
+
"step": 90500
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 5.838225387354441,
|
| 1513 |
+
"grad_norm": 0.910997211933136,
|
| 1514 |
+
"learning_rate": 0.0004109578494899596,
|
| 1515 |
+
"loss": 0.2326,
|
| 1516 |
+
"step": 91000
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 5.870304430115805,
|
| 1520 |
+
"grad_norm": 1.2072116136550903,
|
| 1521 |
+
"learning_rate": 0.00040881931524133357,
|
| 1522 |
+
"loss": 0.2351,
|
| 1523 |
+
"step": 91500
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 5.902383472877169,
|
| 1527 |
+
"grad_norm": 1.1762892007827759,
|
| 1528 |
+
"learning_rate": 0.00040668078099270766,
|
| 1529 |
+
"loss": 0.2323,
|
| 1530 |
+
"step": 92000
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 5.9344625156385336,
|
| 1534 |
+
"grad_norm": 1.4378530979156494,
|
| 1535 |
+
"learning_rate": 0.00040454224674408163,
|
| 1536 |
+
"loss": 0.2347,
|
| 1537 |
+
"step": 92500
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 5.966541558399897,
|
| 1541 |
+
"grad_norm": 1.3818738460540771,
|
| 1542 |
+
"learning_rate": 0.0004024037124954556,
|
| 1543 |
+
"loss": 0.234,
|
| 1544 |
+
"step": 93000
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 5.998620601161261,
|
| 1548 |
+
"grad_norm": 1.3341606855392456,
|
| 1549 |
+
"learning_rate": 0.0004002651782468297,
|
| 1550 |
+
"loss": 0.2309,
|
| 1551 |
+
"step": 93500
|
| 1552 |
+
}
|
| 1553 |
+
],
|
| 1554 |
+
"logging_steps": 500,
|
| 1555 |
+
"max_steps": 187044,
|
| 1556 |
+
"num_input_tokens_seen": 0,
|
| 1557 |
+
"num_train_epochs": 12,
|
| 1558 |
+
"save_steps": 500,
|
| 1559 |
+
"stateful_callbacks": {
|
| 1560 |
+
"TrainerControl": {
|
| 1561 |
+
"args": {
|
| 1562 |
+
"should_epoch_stop": false,
|
| 1563 |
+
"should_evaluate": false,
|
| 1564 |
+
"should_log": false,
|
| 1565 |
+
"should_save": true,
|
| 1566 |
+
"should_training_stop": false
|
| 1567 |
+
},
|
| 1568 |
+
"attributes": {}
|
| 1569 |
+
}
|
| 1570 |
+
},
|
| 1571 |
+
"total_flos": 1.5443526058560717e+18,
|
| 1572 |
+
"train_batch_size": 1,
|
| 1573 |
+
"trial_name": null,
|
| 1574 |
+
"trial_params": null
|
| 1575 |
+
}
|
checkpoint-93522/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:327377c484285f7f445b4af0ca017e44b4d38ade546144ab1b0fdfff6baaffd9
|
| 3 |
+
size 5969
|